fdo-mirrors/mesa
1
0
Fork 0
mirror of https://gitlab.freedesktop.org/mesa/mesa.git synced 2026-05-09 04:38:03 +02:00
Code Issues Projects Releases Packages Wiki Activity Actions 1

gm107/ir: emit RED instead of ATOM when no dst

Browse source 
This is similar to NVC0 and GK110 emitters where we emit
reduction operations instead of atomic operations when the
destination is not used.

Found after writing some tests which check if performance counters
return the expected value. In that case, gred_count returned 0
on gm107 while at least gk106 returned the correct value.

Signed-off-by: Samuel Pitoiset <samuel.pitoiset@gmail.com>
Reviewed-by: Ilia Mirkin <imirkin@alum.mit.edu>
This commit is contained in:
Samuel Pitoiset 2016-11-04 20:08:57 +01:00
parent cfb5a9ab23
commit a295364596
1 changed files with 28 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

29
src/gallium/drivers/nouveau/codegen/nv50_ir_emit_gm107.cpp
View file

@ -180,6 +180,7 @@ private:
void emitIPA();
void emitATOM();
void emitATOMS();
void emitRED();
void emitCCTL();
void emitPIXLD();
@ -2495,6 +2496,29 @@ CodeEmitterGM107::emitATOMS()
emitGPR (0x00, insn->def(0));
}
void
CodeEmitterGM107::emitRED()
{
unsigned dType;
switch (insn->dType) {
case TYPE_U32: dType = 0; break;
case TYPE_S32: dType = 1; break;
case TYPE_U64: dType = 2; break;
case TYPE_F32: dType = 3; break;
case TYPE_B128: dType = 4; break;
case TYPE_S64: dType = 5; break;
default: assert(!"unexpected dType"); dType = 0; break;
}
emitInsn (0xebf80000);
emitField(0x30, 1, insn->src(0).getIndirect(0)->getSize() == 8);
emitField(0x17, 3, insn->subOp);
emitField(0x14, 3, dType);
emitADDR (0x08, 0x1c, 20, 0, insn->src(0));
emitGPR (0x00, insn->src(1));
}
void
CodeEmitterGM107::emitCCTL()
{
@ -3237,7 +3261,10 @@ CodeEmitterGM107::emitInstruction(Instruction *i)
if (insn->src(0).getFile() == FILE_MEMORY_SHARED)
emitATOMS();
else
emitATOM();
if (!insn->defExists(0) && insn->subOp < NV50_IR_SUBOP_ATOM_CAS)
emitRED();
else
emitATOM();
break;
case OP_CCTL:
emitCCTL();